A Prototype Decision Support System for Optimizing the Effectiveness of Elearning in Educational...

8/6/2019 A Prototype Decision Support System for Optimizing the Effectiveness of Elearning in Educational Institutions

http://slidepdf.com/reader/full/a-prototype-decision-support-system-for-optimizing-the-effectiveness-of-elearning 1/13

International Journal of Data Mining & Knowledge Management Process (IJDKP) Vol.1, No.4, July 2011

DOI : 10.5121/ijdkp.2011.1401 1

A PROTOTYPEDECISION SUPPORT S YSTEM

FOR OPTIMIZING THEEFFECTIVENESSOF E-

LEARNING INEDUCATIONAL INSTITUTIONS

S. Abu-Naser1, A. Al-Masri2, Y. Abu Sultan3, I. Zaqout4

1Faculty of Engineering & IT, Department of Information Technology.Al Azhar University Gaza, Palestine,

[email protected] 2Faculty of Engineering & IT, Department of Information Technology.

Al Azhar University Gaza, Palestine,[email protected]

3Faculty of Engineering & IT, Department of Information Technology.

Al Azhar University Gaza, Palestine,[email protected]

4Faculty of Engineering & IT, Department of Information Technology.Al Azhar University Gaza, Palestine,

[email protected]

A BSTRACT

In this paper, a prototype of a Decision Support System (DSS) is proposed for providing the knowledge for

optimizing the newly adopted e-learning education strategy in educational institutions. If an educational

institution adopted e-learning as a new strategy, it should undertake a preliminary evaluation to determine

the percentage of success and areas of weakness of this strategy. If this evaluation is done manually, it would not be an easy task to do and would not provide knowledge about all pitfall symptoms. The proposed

DSS is based on exploration (mining) of knowledge from large amounts of data yielded from the operating

the institution to its business. This knowledge can be used to guide and optimize any new business strategy

implemented by the institution. The proposed DSS involves Database engine, Data Mining engine and

Artificial Intelligence engine. All these engines work together in order to extract the knowledge necessary

to improve the effectiveness of any strategy, including e-learning

K EYWORDS

DSS, E-learning, knowledge, Database, Data mining, Artificial Intelligence.

1. INTRODUCTION

In this section we describe the motivation and the main objectives of Decision Support System(DSS)[1] supporting decision making by providing necessary information needed to be known bydecision makers in order to optimize any new adopted strategy related to learning systems ineducational institutions. E-learning is a new education paradigm used in many educationalinstitutions across the world. According to the rapid development of digital media technology, itis normally most of the educational institutions tending to employ this technology for deliveringthe learning to the students. So adopting the e-learning as new education strategy is an importantdecision in the institution life. If an educational institution adopts the e-learning as a new strategy,




2

it should be applied as experiment and an initial evaluation should be carried out to determine thesuccess rate and the pitfalls of this experiment. When this evaluation is done manually, it wouldnot be an easy task to do and would not provide summary information (knowledge) about allpitfall symptoms. So without that knowledge, there is a risk and the managing of the institutionworkload, which E-learning is part of, is always difficult and complex task. To achieve that task,

the institution managers need current, consistent, reliable information and knowledge about areasof pitfalls and success for the institution workload. Large amounts of data are collected byrunning the institution to its workload. These huge amounts of data, coupled with the need forpowerful computer-based systems for exploring the knowledge helping the institution managersin making decisions, has been described as a "data rich but information poor" situation [2].Building such systems is very important key in providing the required knowledge for developingand optimizing institution strategies alignment with the institution goals.

Optimizing an e-learning strategy requires discovering the knowledge which pitfall symptomsgreatly contribute in the failure of the e-learning. The required knowledge should containcomplete information about the following :

• Who are the frequently failing students in the e-learning courses?

• What are the characteristics of those students?• Who are the inactive students in using e-learning course means?• How do we find clusters of student with similar learning characteristics?• Is there association between student's exam results and student's visiting times for a

courseware in web-based educational system?• Is a particular means of e-learning would be suitable for teaching a specific course for a

target group of students holding certain characteristics?• What are the reasons of noticeable difference in the success ratios for teaching some

courses by the same teacher or different teachers?• Are these reasons related to the students, or the teachers, or the course curriculums and

its assessment ways, or to the used e-learning means?• Is there big negative deviation in e-learning courses enrollment?

These above questions are part of what the educational institution managers need to know, if thequestions answers are completely known, the institution mangers will be able to overcome thefounded pitfalls and the e-learning can be more successful and more vital as the educationalinstitutions move from an 'early adopter' stage to a more general offering . So to know theanswers of these questions, the institution should have a computer-based system exploring thisknowledge from the operating data stored in its Database system. This type of systems is knownas type of Knowledge-discovery systems or in other words data mining systems, or DecisionSupport Systems.

The objective of this paper is to propose a prototype of Decision Support System for educationalinstitutions. The proposed DSS is based on exploration or mining of knowledge from largeamounts of data. The proposed DSS involves Database (DB) engine, Data Mining (DM) engine

and Artificial Intelligence (AI) engine. All these engines work integrally together in order toextract the knowledge necessary to improve the effectiveness of any institution strategy, includingthe e-learning.

1.1. E-learning

Electronic learning or E-learning can be defined as learning delivered by electronic meansincluding CD-ROM, Internet, and Intranet [3]. The two top-most used e-learning deliverymethods are as follows:




3

i. Synchronous e-learning, such as virtual classrooms supporting on-line training.

ii. Asynchronous e-learning, such as web-based courses supporting self-study training.

There are different factors, should be considered when e-learning process is designed, including

such as learning content, instructional methods, e-learning media, learner differences andenvironment. Designing the proper courseware specific to the desired outcome, lessons shouldinclude instructional methods suitable to learner's characteristics. The environment plays alsovital role in success of e-learning, including issues technical constrains related delivery platform,network, software and cultural factors in insinuations [3]. The correct design of the e-leaningprocess will make it unique and more successful, so there are many sides or factors should beviewed and considered in planning and designing a proper e-learning system fitting the learnerneeds. So, we propose DSS for providing some of the information required in optimizing andrefining the learning system, when it is adopted and applied.

1.2. Data Mining

Data mining is one of the rapidly growing fields in computer industry, according to the big sizeand complexity of databases yielded by running institutions to its business [2,22,23,24]. Newmethods for data mining in databases have been studied, which describe data exploring andknowledge extracting processes including data preprocessing, data analysis, and methods of knowledge representation. The common tasks of data mining include induction of classificationmodels [4], association rules [5, 25], evolution and deviation analysis and making clustering forsimilar data objects [2]. To make data firm suitable for mining, preparing methods should beapplied to it for cleansing and transforming to a format ready for the mining [2]. EducationalData mining [6, 26] is a novel research area offering solid ground for applications interested foreducational environment. Educational data mining can mine information (knowledge) related tolearning process activities. In this approach, for example, it is, in promising way, able to extractuseful information, specifically and not to limit, about how student's exam results related to thestudent's visiting times for a courseware in web-based educational system. In section 3 wedescribe our proposed decision support system and how its data mining engine can provide suchthat information.

1.3. Artificial Intelligence

Artificial Intelligence (AI) systems are knowledge processing systems [7]. Knowledgerepresentation, knowledge acquisition, and inference including search and control, are the threemain techniques in AI.

• Knowledge representation. Data mining seeks to discover interesting patterns from largevolumes of data. These patterns can take various forms, such as association rules,classification rules, and decision trees, and therefore, knowledge representation becomesan issue of interest in data mining.

• Knowledge acquisition. The discovery process shares various algorithms and methods

with machine learning for the same purpose of knowledge acquisition from data orlearning from examples.

• Knowledge inference. The patterns discovered from data need to be verified in variousapplications and so deduction of mining results is an essential technique in data miningapplications.




4

Therefore, knowledge representation, knowledge acquisition and knowledge inference, the threefundamental techniques in AI are all relevant to data mining.

1.4. Decision Support System

Decision Support Systems have been studied, in the 1960s, as how to use computerized models toassist in decision making and planning [8]. A decision support system is an interactive computer-based system designed to serve the management level of the organization in performing computergenerated analysis of its own business data [1]. A decision support system is a general term forany computer application enhancing the business manager's ability to make decision. DSS assiststhe mangers to make decisions that are unique, swiftly changing and not easily specified inadvance [19]. Although DSS use internal information from transaction processing systems andmanagement information systems; they often bring in information from external sources such asserver log files. Decision Support System is designed to facilitate the input data and editing data,the execution of the required models necessary to analyze the data, and display the results inunderstandable formats. Developments in information science and computer industry are having asignificant impact on contributing in building of decision support systems, so many of contributing discipline's approaches could be utilized in building decision support systems thatare known as hybrid decision support systems of multiple approaches. Our proposed DSS hostsand combines the facilities of three distinct discipline's approaches, databases management, datamining, and AI, to develop hybrid decision-making mechanisms. So using these disciplines helpssolve abroad range of the institution's problems in decision making.

2. RELATED WORK

Decision support systems play vital role in educational institutions. Sanjeev and ZythKow [9]apply knowledge discovery to data of university database, the knowledge is presented touniversity administrator in order to make strategic decision for the institutional policies. Luan[10] proposed using different data mining algorithms for doing a comprehensive analysis of student characteristics in order to improve the effectiveness of alumni development. Deniz andErsan [11, 12] proposed a DSS for student, course and program assessment. Minaei-Bidgoli andPunch [13] proposed a classification model for predicting student final grades and the studentattributes extracted from the logged file is used in order to build this model. Dasgupta andKhazanchi [14] described an Intelligent Agent Enabled Decision Support (IAEDS) system, whichassist in making strategic decisions for scheduling academic courses. Scholl [15] presented DSSfor assessing educational capacity and planning its distribution and utilization.

Nwelih, and Chiemeke [20] proposed an Academic Advising Decision Support System forNigerian Universities. Zorrilla and others [21] described a proposal of a decision making systemwhich helps distance instructors to know who their students are, how they work, how they use thevirtual course, where they find the problems and so on, and in this way, instructors can act assoon as they detect any difficulty, for example, proposing new tasks, re-organizating the content-pages, adding new information, opening discussions and so on. Likewise they proposed somequestions that, in their opinion, are of interest to teaching staff and show how the answers arevery useful for improving the learning and teaching process. These answers are obtained bymeans of data mining techniques. Lastly, they also suggested a modular architecture for itsimplementation.

3. PROPOSED DSS PROTOTYPE

This section describes the architecture's components of the proposed DSS prototype and describeshow these components are integrated together to perform tasks embedded in a requested user'squery.




5

Achievement of the user's query during the proposed system is going through four phases of thework described in section 3.2.

3.1 DSS Prototype Architecture

As shown in Figure 1, the DSS integrates three main components, Database engine, Data Miningengine, and AI engine. For some tasks, including data extracting, transforming, and loading. TheDSS integrates ETL (Extract, Transform, Load) tool for extracting a task–relevant data fromoperational database, and transforming it to suitable formats and loading into the DSS's data store.The DSS's data store could be involved in relational database store or multidimensional database(data cube) that is the core database schema of data Warehouse [16,17].

Figure 1. A chart of the major components in the proposed DSS architecture.

When a decision-maker makes his requested queries, these queries would be handled by a queryhandler tool that is one of the integrated DSS's components. The query handler parses and

forwards the handled queries in terms of AI specifications. All information and requests aboutDSS tasks to be performed are placed on a knowledge-base store managed by the AI engine,where the AI engine can view them. The AI engine coordinates the tasks of requests, and utilizesthe knowledge-base to justify whether a particular request is AI task or it is data mining task. TheAI engine forwards the data mining tasks to the data mining engine for processing, the datamining engine delivers results of its assigned tasks to the AI engine to deal with these resultslater.

AI engine treats the results of the executed tasks as possible as follows:

i. Converting the results to AI facts and storing these facts in a knowledge-base store.

ii. Presenting the results on user interface in intelligence user-preferable format.

3.2 DSS Prototype Architecture Phases

The DSS prototype architecture includes four phases: initial, justification, execution, andpresentation phases. Figure 2 depicts these phases and their functional steps.

i. Initial phase: in this phase, the query handler converts user query to query in terms of AI specifications, and sends it to AI engine.




6

ii. Justification and creation phase: the AI engine justifies the assigned query to identifyit whether it is AI task or it is mining task. The justification result is used to create AItask, or data mining task. The created task is assigned to the corresponding engine toexecute it.

iii. Execution phase: AI engine and data mining engine achieve their assigned tasks. Theexecuted task results are stored as knowledge facts in the knowledge-base store, orsent to a presentation module in the fourth phase to create the proper interface to showthem.

iv. Presentation phase: in this phase, AI presentation module generates the properinterface for the executed task results.

Figure 2. The proposed DSS architecture phases and their functional steps.

Different software modules should be designed in order to perform the procedures of the fourthphase that are illustrated in Figure 3.The details for functional steps of these modules, and DSSstores are summarized in Table 1.

Table 1. The Functional steps of modules and DSS stores

Module Functional steps

User QueryHandler Module

User Query Handler Module through its GUI enables the User toenter the required query. A query parsing is achieved to convert theuser query into a specific query in AI syntax, and then the UserQuery Handler Module forwards the parsed query to justificationmodule to validate it.

AI JustificationModule

A justification module justifies the query to validate itsconsistency, and for identifying the query's task functionality bymatching the query specification with task specification rulesstored in the Task-knowledge domain. as well, JustificationModule lookups in Task-knowledge domain to detect previouslycreated task with similar to the requested functionality in thecurrent query. The Justification outcome is sent to AI CreationModule for creating the query's functionality task in a proper way.




7

AI CreationModule

A creation module creates a task for performing the specificfunctionality requested in the query. The functionality of the querycould be AI functionality, or data mining functionality, so thecreation module could create an AI task, or a data mining taskcorresponding to the requested functionality. A creation module,

before the task creation, utilizes justification outcome, which tellsit that there is found a task previously created with similar to therequested functionality in the current query, or there is not. If suchthat task is found, the creation module will clone it and adapt itwith the new parameters of the current query. If a task with therequested functionality is not found, the creation module willcreate a new task and store its information in the Task-knowledgedomain. According to the type of the created task, the created taskis forwarded to AI Functionality Module, or to Data MiningFunctionality Module for executing it.

AI Functionality

Module

AI Functionality Module includes set of AI functions. Theforwarded created task, from AI Creation Module, is executed byrunning one of these functions. AI Functionality Module includes

functionalities needing to access the DSS data that is pre-preparedin advance for making it suitable for applying these functionalities.

Data MiningFunctionality

Module

A data mining functionality module includes set of Data Miningfunctions. The forwarded created task, from AI Creation Module,is executed by running one of these functions. Data miningFunctionality Module includes functionalities needing to accessthe DSS data, that is loaded from operational database.

AI PresentationModule

AI Presentation Module generates intelligent graphical userinterfaces showing the knowledge yielded from executing tasksspecified in the user-query.

Knowledge-Base

stores

Knowledge-Base stores contain Knowledge and rules of task, data,and data mining domains. Initially DSS developer providesKnowledge-Base stores with knowledge and rules. Knowledge-Base store is updated by adding new knowledge and rules obtainedfrom executing the DSS tasks.

DSS data stores

DSS data stores are provided with information obtained fromhistorical data, or from current data. The data stored in DSS datastore should pre-prepared in advance for making it suitable forapplying DSS tasks.

In summary of the above, the main objective of the proposed DSS architecture is to utilize andcombine the advantages of AI, and Data mining functionalities in integrated and promising way.The proposed system could be developed as a four-tier architecture as shown in Figure 3.




8

Figure 3. Four-tier architecture of the proposed DSS

4. EMPLOYING THE PROPOSED DSS IN EDUCATIONAL INSTITUTIONS

In this section, we demonstrate how the proposed DSS could contribute in providing theknowledge necessary to educational institution's managers for making the correct decisions tooptimize the educational systems, including e-learning. Figure 4 shows how the usage of theproposed DSS in educational institutions forms an interactive cycle for a learning refinement.

Figure 4. The cycle of employing the proposed DSS in educational institutions

4.1 Examples of Queries In The DSS

In this section, we give some examples of queries describing about requested information of whatthe educational institution's managers need to know, and of what the proposed DSS can provide.

Example 1: Query for describing general characteristics of students in the university database.The functionality of this query is data generalization which is most popularly used data miningfunction. The function collects task-relevant data to generalize it form low conceptual level tohigher one. For example, the general characteristics of the student in university can be described




9

as a set of characteristic rules or a set of generalized summary tables. The Attribute-OrientedInduction (AOI) method [18] is one of data mining techniques used in data generalization. TheAOI method collects initial task-relevant data relation as shown in table 2, and uses theknowledge base of concept hierarchies of the task-relevant attributes to generalize its concepts.Based on the analysis of the number of distinct values in each attribute, the AOI method

determines generalization plan describing an attribute removal or not?, or how high to generalizethe attribute if it is not a removal. The generalization's plan description is shown in the last row of table 2.

Table 2. Initial relation of query in example #1

Based on the generalization plan, the AOI method performs generalization by attribute removal orattribute generalization, and produces prime generalized relation as shown in table 3. The AOImethod applies aggregation with adjusted levels by merging identical generalized tuples, andaccumulating their respective counts as shown in table 4.

Table 3. Prime generalized relation of query in example #1

Table 4. High-level generalized relation of query in example #1

Example 2: Query for finding the correlations between student's exam scores and their visitingbehavior for a particular courseware in the web-based educational system used in the university.




10

This type of queries, studying the student behavior and the usage of the web-based educationalsystem, are often considered as starting point of evaluation an e-learning system.

The main functionality of the query is mining association [5], considered as one of the top-mostused data mining functionalities. To answer this query, the proposed DSS should prepare, collect

and store the data that would be mined later by analyzing and parsing the server log file of acourseware website. These prepared and collected data describing the student's visiting behaviorwould contain values of indicators about who, when, and how the courseware website is visited.The association mining function mines the task-relevant data derived from merging the prepareddata of the web log files and the data about the student exam scores. Processing the associationmining function on these data, may be present frequent and strong association rules among thebrowsing student behavior's indicators and the student exam scores.

Example 3: Query for presenting usage statistics of the web-based educational system.

The proposed DSS may be process statistics, evolution and deviation analyzes on the dataprepared from parsing the server log files of the web-based system. The outcome of thisanalyzing process could be presented in suitable and readable GUI formats. For example, some of

these GUI formats:

i. Chart presenting count of the courseware's visits for each student, or course.ii. Chart presenting count of the courseware's visits for each courseware components

on the course website.iii. Chart presenting the website usage evolution or deviation for each student, or course.

Example 4: Query for identifying the range of accumulative average score for a particularstudent in specific course.

The proposed DSS scans and parses the log files of an educational web-based server that is usedto offer the student with all lectures of a specific subject online in a video format. The outcome of the scanning and parsing of the log files such as login id, login date, login time, time taken to

view a specific video are all stored in a database. The AI engine receives the stored informationas facts and matches them with the stored rules in the knowledge base to predict the range of theaverage score for a particular student in specific course. The knowledge base was built using thehistory of students in log files and grades received for the same subject.

5. CONCLUSIONS & FUTURE WORK

In this paper, building DSS for educational institutions is proposed to improve learning systemsincluding e-learning. The building of the DSS is based on utilizing functionalities of database, AI,and data mining engines in integrated way. Integrating several AI and data mining functionalitiesinto a single system like the proposed DSS will be promising. The main fundamentals for thisintegration are the rich DSS with extendable knowledge-base and internal well-prepared datamodel, and using self-directed distributed modules. The AI engine plays core role as coordinator

and executer for the most of the DSS tasks including the presentation of the task results inintelligent format.

The foundation of such DSS systems in educational institution will provide the academicpersonnel responsible in that institution with the needed information necessary in optimizing theeducational systems. Even though the proposed prototype is not implemented yet, we hope thatour proposed system goals enable the educational institutions realize the importance of the DSS-produced information in optimizing their adopted learning strategies. Moreover, we plan to




11

implement the modules of the proposed system in order to reach to the overall implementedsystem in future.

REFERENCES

[1] Power, D.J., (2002) Decision Support Systems: Concepts and Resources for Managers. QuorumBooks/Greenwood Publishing.

[2] Han, J. and M. Kamberm (2006). Data mining: concepts and techniques. Amsterdam; Boston SanFrancisco, CA, Elsevier; Morgan Kaufmann.

[3] Clark, R. C., & Mayer, R. E., (2003). e-Learning and the Science of Instruction: ProvenGuidelines for Consumers and Designers of Multimedia Learning. San Francisco: Jossey-Bass.

[4] Kamber, M., Winstone, L., Gong, W., Cheng, S. and Han, J. (1997). Generalization and decisiontree induction: efficient classification in data mining. In 7th International Workshop on ResearchIssues in Data Engineering (RIDE '97) High Performance Database Management for Large-ScaleApplications, pp.111.

[5] Agrawal, R., Imielinski,T. and Swami, A., (1993), Mining association rules between sets of itemsin large databases In Prooc. of the ACM SIGMOD Int'l Conf. on Management of Data (ACMSIGMOD '93), Washington, USA.

[6] MERCERON, A. and YACEF, K,. (2005). Educational Data Mining: a Case Study. In ArtificialIntelligence in Education (AIED2005), C.-K. LOOI, G. MCCALLA, B.

[7] Russell S., Peter Norvig, P., (2010), Artificial intelligence: a modern approach, 3rd edition,Prentice Hall.

[8] Power, D.J., A Brief History of Decision Support Systems, DSSResources.COM, World-WideWeb, (2011),http://dssresources.com/history/dsshistory.html, version 2.6

[9] Sanjeev, P. and Zytkow, J.M., (1995). Discovering enrollment knowledge in university databases.In KDD, pp. 246-251.

[10] Luan, J., (2002).Data mining, knowledge management in higher education, potential applications.In workshop associate of institutional research international conference, Toronto, pp. 1- 18.

[11] Deniz, D.Z. and Ersan, I., (2001) Using an academic DSS for student, course and programassessment, International Conference on Engineering Education, Oslo, pp.6B8-12–6B8 17.

[12] Deniz, D.Z. and Ersan, I., (2002). An academic decision-support system based on academicperformance evaluation for student and program assessment, International Journal of EngineeringEducation, Vol. 18, No. 2, pp.236–244.

[13] Minaei-Bidgli, B. and Punch,W.,(2003). Using genetic algorithms for data mining optimizing inan educational web-based system. In GECCO, pp. 2252-2263.

[14] Dasgupta, P. and Khazanchi, D., (2005). Adaptive decision support for academic coursescheduling using intelligent software agents. International Journal of Technology in Teaching andLearning, Vol. 1, No 2,pp., 63-78.

[15] Mansmann, S. and Scholl, M. H., (2007 ). Decision Support System for Managing EducationalCapacity Utilization in Education, IEEE Transactions Vol. 50, No. 2, pp. 143 – 150.

[16] Inmon, W.H. and Kelley, C., (1993). Rdb/VMS: Developing the Data Warehouse. QEDPublishing Group, Boston.

[17] Agrawal, R., Gupta, A., and Sarawagi, S., (1995). Modeling multidimensional databases. IBMResearch Report.

[18] Han, J.; Cercone, N. and Cai, Y., (1991). Attribute-Oriented Induction in Relational Databases InG. Piatetsky-Shapiro and W. J. Frawley, editors, Knowledge Discovery in Databases, pp. 213-228.

[19] Lauden, K. and Lauden J., (2009). Management information Systems. Prentice Hall; 11th edition.




12

[20] Nwelih, E. and Chiemeke, S.C. (2010) Academic Advising Decision Support System for NigerianUniversities, Anthology of Abstracts of the 3rd International Conference on ICT for Africa, March25-27, Yaoundé, Cameroon. Baton Rouge, LA: International Center for IT and Development.

[21] Marta Zorrilla, Diego García and Elena Álvarez.(2010). A Decision Support System to improve e-Learning Environments. BEWEB 2010 - International Workshop on Business intelligence and the

WEB ,March 22-26, 2010 - Lausanne (Switzerland). [22] Roberto Llorente and Maria Morant, (2011), Data Mining in Higher Education, Kimito Funatsu,

InTech, 2011.

[23] Falakmasir M., and Habibi J., (2010), Using Educational Data Mining Methods to Study theImpact of Virtual Classroom in E-Learning, Educational Data Mining 2010, 3rd InternationalConference on Educational Data Mining , Pittsburgh, PA, USA, June 11-13, 2010.

[24] Rajibussalim M., (2010), Mining Students’ Interaction Data from a System that Support Learningby Reflection, Educational Data Mining 2010, 3rd International Conference on Educational DataMining , Pittsburgh, PA, USA, June 11-13, 2010.

[25] Kumar R. and Chadrasekaran R.,(2011), Attribute Correction - Data Cleaning Using AssociationRule and Clustering Methods, International Journal of Data Mining & Knowledge ManagementProcess (IJDKP). Vol(1),No(2).

[26] Srinivas K., Raghavendra G. and Govardhan A., (2011), Survey on Prediction of Heart MorbidityUsing Data Mining Techniques, International Journal of Data Mining & Knowledge ManagementProcess (IJDKP). Vol(1),No(3).

Authors

1- Samy Saleem. Abu Naser was born in Gaza, Palestine, in 1964. He receivedthe B.S. & M.S. degrees in Computer Science from the University of WesternKentucky, USA in 1987 and 1989 respectively and the Ph.D. degree from NorthDakota State University, USA in 1993 in Computer Science. He has beenworking as Associate Professor in Faculty of Engineering and InformationTechnology, Al-Azhar University, Gaza, Palestine since 2007. He wasappointed as assistant professor in Al Azhar University 1996-2006. He wasappointed as a Teaching Assistant at the University of Western Kentucky, USA,1988-1989. He was appointed as a Research Assistant at the North Dakota StateUniversity, USA, 1990-1993. He has worked as Field Information Systems Officer at the United NationsRelief and Works Agency, Gaza 1993-1996. His areas of interest are Artificial Intelligence, IntelligentTutoring Systems, Expert Systems, Knowledge Management Systems, and Compiler Design.

2- Abedelbaset Rajab Almasri was born in AL-Maghazi, Gaza, Palestine, in1978. He received the B. S. in Computer Science from Al Azhar University,Palestine in 2000 and M.S. in Computer Science from Vrije University Brusselin 2006. He was appointed the head of the Department of InformationTechnology in the Faculty of Engineering and Information Technology Al AzharUniversity since 2010. He has been working as lecturer in the Department since2006. He has worked as A Teaching Assistants in Al Azhar University betweenthe years 2000 and 2005.




13

3- Yousef Shafiq Abu Sultan was born in Nusirate, Gaza, Palestine, in 1970. Hereceived the B. A. in Business Administration from Birziet University, Palestinein 1995 and MBA from Islamic University, Palestine in 2004. He has beenworking as lecturer in the Faculty of Engineering and Information Technology,Information Technology Dept., Al-Azhar University, Gaza, Palestine since 2006.He was appointed as a senior investment & financial analyst PED. CO, Gaza

2005-2006. He was appointed as a Branch Manager of Management ConsultingServices Company (M.C.S.) from 1996-2005 in Gaza Strip. Further more, he wasappointed as a Trainer, Training consultant for many Governmental and nonGovernmental organization from 1997-2006.

4- Ihab S. Zaqout was born in Libya in 1965. He received the B. S. inComputer Science from the University of Al-Fateh, Libya, in 1987 and the M.S.degree in Computer Science from Jordan University, Jordan in 2000 and thePh.D. in Computer Science from the University of Malaya, Malaysia in 2006.He has been the Dean of the Faculty of Engineering and InformationTechnology in Al Azhar University, Gaza, Palestine since 2010. He wasappointed the head of the Department of Information Technology during theyears 2008-2010. He has been working as assistant professor in the Department

Information Technology since 2006.

Date post:	07-Apr-2018
Category:	Documents
Upload:	lewis-torres
View:	218 times
Download:	0 times

A Prototype Decision Support System for Optimizing the Effectiveness of Elearning in Educational...

Documents